Method and apparatus for outputting information
View Patent ↗Embodiments of the present disclosure relate to a method and apparatus for outputting information. The method includes: outputting a to-be-read audio in response to receiving a reading instruction from a user; acquiring an actually read audio obtained by reading the to-be-read audio by the user; performing speech recognition on the actually read audio to obtain a recognition result; calculating a similarity between the actually read audio and the to-be-read audio based on a character string corresponding to the recognition result and a character string corresponding to the to-be-read audio; determining, from a predetermined set of similarity intervals, a similarity interval to which the calculated similarity belongs; and outputting a reading evaluation corresponding to the determined similarity interval. The embodiment may help a reader to improve the learning efficiency and learning interest, thereby improving the rate of a user using a device.
1. A method for outputting information, comprising:
outputting a to-be-read audio in response to receiving a reading instruction from a user;
acquiring an actually read audio obtained by reading the to-be-read audio by the user;
performing speech recognition on the actually read audio to obtain a recognition result;
calculating a similarity between the actually read audio and the to-be-read audio based on a character string corresponding to the recognition result and a character string corresponding to the to-be-read audio;
determining, from a predetermined set of similarity intervals, a similarity interval to which the calculated similarity belongs; and
outputting a reading evaluation corresponding to the determined similarity interval.
2. The method according to claim 1 , wherein the calculating the similarity between the actually read audio and the to-be-read audio based on the character string corresponding to the recognition result and the character string corresponding to the to-be-read audio comprises:
in response to determining that the recognition result indicates the actually read audio being a Chinese audio and the to-be-read audio is an English audio or a Chinese audio, determining a phonetic character string corresponding to the to-be-read audio, and determining a phonetic character string corresponding to the recognition result; and
calculating the similarity between the actually read audio and the to-be-read audio based on the phonetic character string corresponding to the to-be-read audio and the phonetic character string corresponding to the recognition result.
3. The method according to claim 1 , wherein the calculating the similarity between the actually read audio and the to-be-read audio based on the character string corresponding to the recognition result and the character string corresponding to the to-be-read audio comprises:
in response to determining that the recognition result indicates the actually read audio being an English audio and the to-be-read audio is a Chinese audio, determining a phonetic character string corresponding to the to-be-read audio, and determining an English character string corresponding to the recognition result; and
calculating the similarity between the actually read audio and the to-be-read audio based on the phonetic character string corresponding to the to-be-read audio and the English character string corresponding to the recognition result.
4. The method according to claim 1 , wherein the calculating the similarity between the actually read audio and the to-be-read audio based on the character string corresponding to the recognition result and the character string corresponding to the to-be-read audio comprises:
in response to determining that the recognition result indicates the actually read audio being an English audio and the to-be-read audio is an English audio, determining an English character string corresponding to the to-be-read audio, and determining an English character string corresponding to the recognition result; and
calculating the similarity between the actually read audio and the to-be-read audio based on the English character string corresponding to the to-be-read audio and the English character string corresponding to the recognition result.
5. The method according to claim 1 , wherein the calculating the similarity between the actually read audio and the to-be-read audio based on the character string corresponding to the recognition result and the character string corresponding to the to-be-read audio comprises:
determining a length of the longest common subsequence between the character string corresponding to the to-be-read audio and the character string corresponding to the recognition result; and
calculating the similarity between the actually read audio and the to-be-read audio based on the length and a length of the character string corresponding to the to-be-read audio.
6. A method for outputting information, comprising:
in response to receiving a reading instruction from a user, outputting a to-be-read audio sequence, and performing following reading steps for each to-be-read audio in the to-be-read audio sequence: outputting the to-be-read audio; acquiring an actually read audio obtained by reading the to-be-read audio by the user; performing speech recognition on the acquired actually read audio to obtain a recognition result; calculating a similarity between the acquired actually read audio and the to-be-read audio based on a character string corresponding to the recognition result and a character string corresponding to the to-be-read audio; determining, from a predetermined set of similarity intervals, a similarity interval to which the calculated similarity belongs; outputting a reading evaluation corresponding to the determined similarity interval; and in response to determining the calculated similarity being less than or equal to a preset similarity threshold, proceeding to perform the reading steps based on the to-be-read audio.
7. The method according to claim 6 , further comprising:
in response to determining the calculated similarity being greater than the preset similarity threshold, proceeding to perform the reading steps based on a to-be-read audio next to the to-be-read audio in the to-be-read audio sequence.
8. An apparatus for outputting information, comprising:
at least one processor; and
a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
outputting a to-be-read audio in response to receiving a reading instruction from a user;
acquiring an actually read audio obtained by reading the to-be-read audio by the user;
performing speech recognition on the actually read audio to obtain a recognition result;
calculating a similarity between the actually read audio and the to-be-read audio based on a character string corresponding to the recognition result and a character string corresponding to the to-be-read audio;
determining, from a predetermined set of similarity intervals, a similarity interval to which the calculated similarity belongs; and
outputting a reading evaluation corresponding to the determined similarity interval.
9. The apparatus according to claim 8 , wherein the calculating the similarity between the actually read audio and the to-be-read audio based on the character string corresponding to the recognition result and the character string corresponding to the to-be-read audio comprises:
in response to determining that the recognition result indicates the actually read audio being a Chinese audio and the to-be-read audio is an English audio or a Chinese audio, determining a phonetic character string corresponding to the to-be-read audio, and determining a phonetic character string corresponding to the recognition result; and
calculating the similarity between the actually read audio and the to-be-read audio based on the phonetic character string corresponding to the to-be-read audio and the phonetic character string corresponding to the recognition result.
10. The apparatus according to claim 8 , wherein the calculating the similarity between the actually read audio and the to-be-read audio based on the character string corresponding to the recognition result and the character string corresponding to the to-be-read audio comprises:
in response to determining that the recognition result indicates the actually read audio being an English audio and the to-be-read audio is a Chinese audio, determining a phonetic character string corresponding to the to-be-read audio, and determining an English character string corresponding to the recognition result; and
calculating the similarity between the actually read audio and the to-be-read audio based on the phonetic character string corresponding to the to-be-read audio and the English character string corresponding to the recognition result.
11. The apparatus according to claim 8 , wherein the calculating the similarity between the actually read audio and the to-be-read audio based on the character string corresponding to the recognition result and the character string corresponding to the to-be-read audio comprises:
in response to determining that the recognition result indicates the actually read audio being an English audio and the to-be-read audio is an English audio, determining an English character string corresponding to the to-be-read audio, and determining an English character string corresponding to the recognition result; and
calculating the similarity between the actually read audio and the to-be-read audio based on the English character string corresponding to the to-be-read audio and the English character string corresponding to the recognition result.
12. The apparatus according to claim 8 , wherein the calculating the similarity between the actually read audio and the to-be-read audio based on the character string corresponding to the recognition result and the character string corresponding to the to-be-read audio comprises:
determining a length of the longest common subsequence between the character string corresponding to the to-be-read audio and the character string corresponding to the recognition result; and
calculating the similarity between the actual read-after audio and the to-be-read audio based on the length and a length of the character string corresponding to the to-be-read audio.
13. An apparatus for outputting information, comprising:
at least one processor; and
a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
outputting a to-be-read audio sequence in response to receiving a reading instruction from a user, and executing following reading steps for each to-be-read audio in the to-be-read audio sequence: outputting the to-be-read audio; acquiring an actually read audio obtained by reading the to-be-read audio by the user; performing speech recognition on the acquired actually read audio to obtain a recognition result; calculating a similarity between the acquired actually read audio and the to-be-read audio based on a character string corresponding to the recognition result and a character string corresponding to the to-be-read audio; determining, from a predetermined set of similarity intervals, a similarity interval to which the calculated similarity belongs; outputting a reading evaluation corresponding to the determined similarity interval; and
in response to determining the calculated similarity being less than or equal to a preset similarity threshold, proceeding to perform the reading steps based on the to-be-read audio.
14. The apparatus according to claim 13 , the operations further comprising:
in response to determining the calculated similarity being greater than the preset similarity threshold, proceeding to perform the reading steps based on a to-be-read audio next to the to-be-read audio in the to-be-read audio sequence.
15. A non-transitory computer readable medium, storing a computer program, wherein the program, when executed by a processor, implements a method comprising:
outputting a to-be-read audio in response to receiving a reading instruction from a user;
acquiring an actually read audio obtained by reading the to-be-read audio by the user;
performing speech recognition on the actually read audio to obtain a recognition result;
calculating a similarity between the actually read audio and the to-be-read audio based on a character string corresponding to the recognition result and a character string corresponding to the to-be-read audio;
determining, from a predetermined set of similarity intervals, a similarity interval to which the calculated similarity belongs; and
outputting a reading evaluation corresponding to the determined similarity interval.